{"title":"利用可解释的机器学习快速筛查有胎盘转移风险的化学品","authors":"Xiaojia Chen, Jingzhi Yao, Yu Ma, Yuanyuan Fang, Wenxin Wang, Xiaojun Deng, Ling Tan, Yi-Jun Fan* and Mingliang Fang*, ","doi":"10.1021/acs.estlett.4c0041310.1021/acs.estlett.4c00413","DOIUrl":null,"url":null,"abstract":"<p >Assessing the placental transfer efficiency of toxic chemicals remains challenging. Here, a robust machine learning (ML) model was developed to predict the human fetal–maternal blood concentration ratio (F/M) at the exposomic level. By curating one of the largest F/M data sets, we evaluated a series of prediction models using a combination of 12 ML algorithms and four molecular fingerprints. The long short-term memory (LSTM) model with retraining optimization works as the best performer, displayed robust accuracy (R<sup>2</sup><sub>train</sub> = 0.91, R<sup>2</sup><sub>test</sub> = 0.68), and was subsequently applied to our previously developed risk-based Human Exposome and Metabolite Database (HExpMetDB). The fetal hazard quotient (FHQ) was assessed using the predicted F/M ratios, probabilistic exposure dose, and toxicity index. From the top 1000 prioritized chemicals via FHQs ranking, we randomly selected four candidates (triethyl phosphate, benzotriazole, oxybenzone, and dichlormid) to perform <i>in vivo</i> experiments. All four chemicals exhibited transplacental potential (F/M ratio >0.3) as new possible chemicals of concern, demonstrating the accuracy of the predictive model. The Shapley additive explanation (SHAP) method revealed the top 10 key structural fragments related to the transplacental transfer efficiency. We believe that the prediction model can serve as an effective tool to screen potential risk compounds of fetal exposure.</p>","PeriodicalId":37,"journal":{"name":"Environmental Science & Technology Letters Environ.","volume":null,"pages":null},"PeriodicalIF":8.9000,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Rapid Screening of Chemicals with Placental Transfer Risk Using Interpretable Machine Learning\",\"authors\":\"Xiaojia Chen, Jingzhi Yao, Yu Ma, Yuanyuan Fang, Wenxin Wang, Xiaojun Deng, Ling Tan, Yi-Jun Fan* and Mingliang Fang*, \",\"doi\":\"10.1021/acs.estlett.4c0041310.1021/acs.estlett.4c00413\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >Assessing the placental transfer efficiency of toxic chemicals remains challenging. Here, a robust machine learning (ML) model was developed to predict the human fetal–maternal blood concentration ratio (F/M) at the exposomic level. By curating one of the largest F/M data sets, we evaluated a series of prediction models using a combination of 12 ML algorithms and four molecular fingerprints. The long short-term memory (LSTM) model with retraining optimization works as the best performer, displayed robust accuracy (R<sup>2</sup><sub>train</sub> = 0.91, R<sup>2</sup><sub>test</sub> = 0.68), and was subsequently applied to our previously developed risk-based Human Exposome and Metabolite Database (HExpMetDB). The fetal hazard quotient (FHQ) was assessed using the predicted F/M ratios, probabilistic exposure dose, and toxicity index. From the top 1000 prioritized chemicals via FHQs ranking, we randomly selected four candidates (triethyl phosphate, benzotriazole, oxybenzone, and dichlormid) to perform <i>in vivo</i> experiments. All four chemicals exhibited transplacental potential (F/M ratio >0.3) as new possible chemicals of concern, demonstrating the accuracy of the predictive model. The Shapley additive explanation (SHAP) method revealed the top 10 key structural fragments related to the transplacental transfer efficiency. We believe that the prediction model can serve as an effective tool to screen potential risk compounds of fetal exposure.</p>\",\"PeriodicalId\":37,\"journal\":{\"name\":\"Environmental Science & Technology Letters Environ.\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":8.9000,\"publicationDate\":\"2024-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Environmental Science & Technology Letters Environ.\",\"FirstCategoryId\":\"1\",\"ListUrlMain\":\"https://pubs.acs.org/doi/10.1021/acs.estlett.4c00413\",\"RegionNum\":2,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ENVIRONMENTAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Environmental Science & Technology Letters Environ.","FirstCategoryId":"1","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acs.estlett.4c00413","RegionNum":2,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}
Rapid Screening of Chemicals with Placental Transfer Risk Using Interpretable Machine Learning
Assessing the placental transfer efficiency of toxic chemicals remains challenging. Here, a robust machine learning (ML) model was developed to predict the human fetal–maternal blood concentration ratio (F/M) at the exposomic level. By curating one of the largest F/M data sets, we evaluated a series of prediction models using a combination of 12 ML algorithms and four molecular fingerprints. The long short-term memory (LSTM) model with retraining optimization works as the best performer, displayed robust accuracy (R2train = 0.91, R2test = 0.68), and was subsequently applied to our previously developed risk-based Human Exposome and Metabolite Database (HExpMetDB). The fetal hazard quotient (FHQ) was assessed using the predicted F/M ratios, probabilistic exposure dose, and toxicity index. From the top 1000 prioritized chemicals via FHQs ranking, we randomly selected four candidates (triethyl phosphate, benzotriazole, oxybenzone, and dichlormid) to perform in vivo experiments. All four chemicals exhibited transplacental potential (F/M ratio >0.3) as new possible chemicals of concern, demonstrating the accuracy of the predictive model. The Shapley additive explanation (SHAP) method revealed the top 10 key structural fragments related to the transplacental transfer efficiency. We believe that the prediction model can serve as an effective tool to screen potential risk compounds of fetal exposure.
期刊介绍:
Environmental Science & Technology Letters serves as an international forum for brief communications on experimental or theoretical results of exceptional timeliness in all aspects of environmental science, both pure and applied. Published as soon as accepted, these communications are summarized in monthly issues. Additionally, the journal features short reviews on emerging topics in environmental science and technology.